Reposted by Olivier BalaisThomas Jarrand @tom32i.bsky.social · 24/09/2026Je viens d'expliquer au produit que c'est mieux de garder un champs unique "Nom et prénom" plutôt que les séparer en utilisant l'argument: "Sinon Zendaya ne peux pas passer de commandes chez nous !" 151
Reposted by Olivier BalaisMickaël Correia @mickacorreia.bsky.social · 25/09/2026La nationalisation de TotalEnergies ne serait pas une "folie" mais juste une correction historique. Le groupe a été créé en 1924 par l'Etat français pour assurer l’indépendance pétrolière pays. Et ce n'est qu'à partir de 1992 que l'Etat a commencé à se retirer réellement de la firme. (1/3) 👇 15483219
Reposted by Olivier BalaisMickaël Correia @mickacorreia.bsky.social · 25/09/2026A lire aussi dans @contretemps-revue.bsky.social,.sur la possibilité matérielle de nationaliser TotalEnergies : www.contretemps.eu/nationaliser...contretemps.euNationaliser TotalEnergies : le temps est venu - ContretempsAlbin Brunet défend la nationalisation de TotalEnergies en s’appuyant sur une analyse détaillée des comptes du groupe, de son histoire institutionnelle et du cadre constitutionnel français. À ce titre... 19430
Reposted by Olivier BalaisCassidy @cassidoo.co · 01/09/2026It's here! It's here!! Add images or video to issues, PRs, and comments via the gh CLI ✨ github.blog/changelog/20...github.blogGitHub CLI: Media in issues, pull requests, and comments - GitHub ChangelogGitHub CLI now has a repeatable --attach flag that uploads a local image or video and references it inline in an issue, pull request, or comment body. This is now… 8796
Reposted by Olivier Balaisnilay patel @reckless.bsky.social · 05/08/2026Sundar politely declining to engage with Demis saying “we are in foothills of the singularity” was a sign, in retrospect 0612
Reposted by Olivier BalaisEuropean Commission @ec.europa.eu · 18/07/2026We aim to make Europe the world’s first electro-powered continent. Our new plan could cut gas demand by two-thirds, halve oil use, and save €260 billion in fossil fuel imports by 2040. How? ↓🧵 1503457828
Reposted by Olivier BalaisÉric D. @edas.survol.fr · 14/07/2026Oh que je déteste ces gens qui, en environnement pro, répondent en copiant collant une longue réponse provenant d'un LLM… Points bonus s'ils ne maîtrisent pas ce qu'ils copient-collent. Arrêtez ça. 0133
Olivier Balais @overnetcity.bsky.social · 03/07/2026Cognition (Devin) raised $1B at a $26B valuation, more than double its September figure. ARR went from $37M to ~$492M in a year, 13x. The market is pricing coding agents as platforms, not features.techcrunch.comhttps://techcrunch.com/2026/05/27/ai-coding-startup-cognition-raises-1b-at-25b-pre-money-valuation/As Cognition reaches $492 million in annualized revenue run rate, it more than doubled its valuation in eight months, it says. 000
Olivier Balais @overnetcity.bsky.social · 01/07/2026METR surveyed 349 technical workers: median self-reported value gain from AI tools is 1.4 to 2x. The same lab's earlier RCT found AI actually slowed experienced devs down. The gap between how productive we feel and how productive we are is the 2026 story.metr.orghttps://metr.org/blog/2026-05-11-ai-usage-survey/A survey of 349 technical workers finds a median 1.4–2x self-reported change in value of work due to AI tools, expected to grow over time, though there are reasons to be skeptical of the magnitude. 000
Olivier Balais @overnetcity.bsky.social · 29/06/2026Anthropic shipped Opus 4.8 just 41 days after 4.7: 4x lower error rate, a fast mode 3x cheaper, and 'dynamic workflows' orchestrating hundreds of background subagents. Running parallel agents went from a power-user hack to a native feature.techcrunch.comhttps://techcrunch.com/2026/05/28/anthropic-releases-opus-4-8-with-new-dynamic-workflow-tool/The new Opus model comes with a tool called Dynamic Workflows, for coordinating swarms of subagents. 100
Reposted by Olivier BalaisMatthieu Napoli @mnapoli.bsky.social · 25/06/2026Introducing VibePHP, a next-gen PHP runtime that runs on vibes and supports generics, async/await and more 🌀 github.com/mnapoli/vib... 🌀 575
Olivier Balais @overnetcity.bsky.social · 26/06/2026Uber capped AI coding tools at $1,500/month per tool after burning its entire 2026 AI budget in four months. Some engineers were running $2,000/month in tokens. The 2026 question isn't 'does agentic coding work', it's 'who pays for it'.techcrunch.comhttps://techcrunch.com/2026/06/02/uber-caps-employee-ai-spending-after-blowing-through-budget-in-four-months/Uber's cutback has occurred after the company had reportedly encouraged staff to use AI as much as possible. 120
Olivier Balais @overnetcity.bsky.social · 24/06/2026Andon Labs let AI agents run a real business for 20M+ tokens. Claude Opus 4.6 set a new high score, $8,017 profit. It also colluded on prices, deceived suppliers and lied about refunds. Long-horizon agents don't crash. They start cutting corners.andonlabs.comhttps://andonlabs.com/blog/opus-4-6-vending-benchClaude Opus 4.6 achieves state of the art on Vending-Bench with $8,017 profit, but exhibits concerning behavior: price collusion, supplier deception, and lying to customers about refunds. 010
Olivier Balais @overnetcity.bsky.social · 22/06/2026Faros AI tracked 22,000 devs across high vs low AI adoption. Throughput jumped 66%. But incidents per PR rose 242%, time-in-review 441%, and 31% of merged PRs got zero review. The bottleneck didn't vanish, it moved to whoever still reads the code.faros.aihttps://www.faros.ai/research/ai-acceleration-whiplash22K developers reveal AI's real impact: 66% throughput gains but incidents rising faster. Get the definitive data on what's working and breaking. 000
Olivier Balais @overnetcity.bsky.social · 19/06/2026Does running LLMs locally save money? William Angel ran the numbers: on an M5 MacBook Pro, local inference comes out to about 3x the cost per token of OpenRouter for comparable models, and roughly half the speed. For 99% of people, local makes no economic sense.williamangel.nethttps://www.williamangel.net/blog/2026/05/17/offline-llm-energy-use.htmlLocal LLMs can be very very cheap 110
Olivier Balais @overnetcity.bsky.social · 18/06/2026Pragmatic Engineer survey, 900+ engineers: AI is shipping more 'slop', duplicated verbose code, weaker abstractions, more bugs. Management optimizes for output and short-term savings, while the maintenance debt lands on the shrinking group that still understands the code.newsletter.pragmaticengineer.comhttps://newsletter.pragmaticengineer.com/p/ai-impact-on-software-engineers-part-2Tradeoffs of AI tooling, why adopting AI at company-level is hard, what’s changed in two years, and more. The third and final part of a series analyzing our 2026 AI survey results 001
Olivier Balais @overnetcity.bsky.social · 16/06/2026Simon Willison: programming languages used to be lock-in, and increasingly they're not. LLMs make porting a whole codebase to another language actually feasible, so a wrong tech choice is far less permanent than it used to be. simonwillison.net/2026/May/14/...simonwillison.netNot so locked in any moreThis Mitchell Hashimoto quote about Bun migrating from Zig to Rust reminded me of a similar conversation I had at a conference last week. I was talking to someone who … 000
Olivier Balais @overnetcity.bsky.social · 15/06/2026Refactoring on staying in control of AI coding: don't read every generated line, review a short ADR instead, the approach, alternatives, consequences and when to reconsider. Immutable, and they steer future agent work too. One team is already at 120+ ADRs.refactoring.fmhttps://refactoring.fm/p/reviewable-adrs-ai-by-default-andMonday Ideas — Edition #209 000
Olivier Balais @overnetcity.bsky.social · 12/06/2026Nous Research's Hermes Agent v0.14 ships a local OpenAI-compatible proxy: 'hermes proxy' turns your Claude Pro, ChatGPT Pro or SuperGrok login into a localhost endpoint, so Codex CLI, Aider and Cline work with no API key. Also adds LSP diagnostics after each file write.github.comhttps://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.16Hermes Agent v0.14.0 (v2026.5.16) Release Date: May 16, 2026 Since v0.13.0: 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community... 010
Reposted by Olivier BalaisAFUP @afup.org · 11/06/2026L'enquête 2026 du baromètre des salaires en PHP a fermé il y a quelques jours. Avec 509 réponses contre 721 en 2025, nous tirons dès maintenant quelques conclusions sur la disponibilité des devs et leurs sources de préoccupation. Une non-participation est elle aussi une information ! buff.ly/Kk5Y1zz 011
Olivier Balais @overnetcity.bsky.social · 10/06/2026Birgitta Böckeler (Thoughtworks) on 'maintainability sensors' for coding agents: wire static analysis, linting and custom rules as feedback loops so the agent self-corrects before a human ever sees the diff. The harness is the real engineering work.martinfowler.comhttps://martinfowler.com/articles/sensors-for-coding-agents.htmlA practical walkthrough of computational sensors on the path to production, with a deep dive on ESLint and static analysis as feedback for coding agents. 000
Reposted by Olivier BalaisLes Joies du Code @lesjoiesducode.fr · 09/06/2026TESTER C'EST DOUTER CÉDRIC 24114
Olivier Balais @overnetcity.bsky.social · 09/06/2026SpaceX's IPO filing reveals Anthropic pays it about $1.25B per month, $15B a year through 2029, to rent GPU compute. For scale: SpaceX (now bundling X and xAI) reports $18B in 2025 revenue, with 77% of costs going to AI.newsletter.pragmaticengineer.comhttps://newsletter.pragmaticengineer.com/p/the-pulse-antigravity-20-takes-ideNegative feedback greets Google’s redesigned AI IDE, why Google’s product ecosystem is so chaotic, Meta cuts 10% of staff as it hits record revenue and profits, and more 000
Olivier Balais @overnetcity.bsky.social · 08/06/2026Google shipped Gemini Omni Flash: edit real video with plain language, where each instruction builds on the last and characters and physics stay consistent across turns. Takes text, image, audio and video in. Rolling out in the Gemini app, Google Flow and YouTube Shorts.blog.googlehttps://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-omni/Introducing Gemini Omni, which allows you to create anything from any input and edit naturally using conversational language. 000
Olivier Balais @overnetcity.bsky.social · 04/06/2026Alice Ryhl (Google, Tokio maintainer): Rust might be the best language for AI agents. The strict compiler gives high-signal feedback an agent can loop on, and the type system blocks whole bug classes by design. 'Do what the compiler says' scales for generated code.newsletter.pragmaticengineer.comhttps://newsletter.pragmaticengineer.com/p/why-rust-is-different-with-aliceAlice Ryhl from Google’s Android Rust team explains why developers love Rust, and what makes the language so powerful for building reliable software. 000
Olivier Balais @overnetcity.bsky.social · 03/06/2026New paper 'Is Grep All You Need?': across harnesses like Claude Code and Codex, plain grep beats vector retrieval for finding facts in long histories. Exact matches on names, paths and error strings beat embedding similarity. RAG isn't the obvious default for code anymore.arxiv.orghttps://arxiv.org/abs/2605.15184Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks… 000
Olivier Balais @overnetcity.bsky.social · 01/06/2026Anthropic now lets Claude agents run tool execution inside your own infrastructure: self-hosted sandboxes (public beta) and MCP tunnels to reach private DBs and APIs over one outbound encrypted connection, no inbound firewall rules. Orchestration stays on their side.thenewstack.iohttps://thenewstack.io/anthropic-mcp-tunnels-sandboxes/Anthropic launches MCP tunnels and self-hosted sandboxes at Cod'e with Claude' conference in London, giving enterprises secure, private AI agent infrastructure. 000
Reposted by Olivier BalaisJérémy DECOOL @jdecool.bsky.social · 13/05/2026🇫🇷 Pentests avec Claude Code: zythom.fr/2026/05/pentests-avec-cla… 011
Reposted by Olivier BalaisAFUP @afup.org · 09/04/2026Fiabilité en production, tests des workflows IA, composition plutôt qu’héritage : dans son interview, @srogier.bsky.social partage des retours très concrets avant son talk lors de l’AFUP Day 2026 Lyon le 22 mai 2026. Prenez vos places, ça s'annonce passionnant ! buff.ly/YbLiUPj 223
Reposted by Olivier BalaisBon Pote @bonpote.com · 24/04/2026Magnifiques, mais en première ligne du réchauffement climatique. Les cerisiers japonais fleurissent de plus en plus tôt, et pourraient bientôt ne plus fleurir du tout. C'est ce que montre une base de données de 1200 ans de floraison des sakuras à Kyoto. Explications : bonpote.com/les-sakuras-... 515972
Reposted by Olivier BalaisPascal MARTIN 😶🌫️ @pascal-martin.fr · 08/04/2026Well, at least, we can still spend 💸 and burn money 💰🔥 on Opus 😅 011
Reposted by Olivier Balaisclubic-off.bsky.social @clubic-off.bsky.social · 07/04/2026La directrice IA d'AMD a analysé près de 7 000 sessions Claude Code. Son verdict : l'outil ne sait plus réfléchir. Et Anthropic accumule les crises au pire moment.clubic.comAMD tire à vue sur Anthropic : Claude Code ne sait plus coderL'outil de codage star d'Anthropic est accusé de bâcler le travail depuis février. Le problème : cette dégradation survient alors que l'entreprise enchaîne fuite de code source, pannes à répétition et afflux record d'utilisateurs. 012
Reposted by Olivier BalaisDavid Pilato 🇪🇺🇫🇷 @pilato.fr · 30/03/2026My hot take on AI in engineering: It's an exoskeleton, not a replacement. 🦾 It gives us the strength to move faster and build bigger, but the human dev is still the one in the pilot's seat making the hard calls. Better tools don't mean fewer engineers—they mean more ambitious projects. 🛠️ 1107
Olivier Balais @overnetcity.bsky.social · 03/04/20262026 dev workflow: 8 Claude Code sessions running in parallel on one wide screen. Next logical step is obviously a cockpit setup with 2 ultra wides. No other way. 100
Olivier Balais @overnetcity.bsky.social · 02/04/202670% of Devin sessions are still human-triggered. Nader Dabit thinks that flips to 10/90 within a year. The interesting part: what engineers do changes more than what agents do. Less code, more system design for autonomous loops.nader.substack.comhttps://nader.substack.com/p/engineering-for-agents-that-never 000
Reposted by Olivier BalaisThomas Jarrand @tom32i.bsky.social · 01/04/2026Imaginez 10 ans plus tard je sors une suite à Curvytron et je l’annonce un 1er avril ? Nan je rigole. Mais imaginez quand même : curvytron2.com 31611
Olivier Balais @overnetcity.bsky.social · 31/03/2026An agent writes 2,000 lines. It's 80% right. Your instinct says ship it. Wrong move. At Semji we now generate multiple implementations of the same feature, compare architectural trade-offs, then pick. Code is disposable. Judgment is the product.youtube.comhttps://www.youtube.com/watch?v=79sDQ7JXVvQ 000
Olivier Balais @overnetcity.bsky.social · 30/03/2026Counter-intuitive: GPT-5.4 produces better frontends with LOW reasoning than high. When the model overthinks, it over-designs. Restraint beats intelligence. OpenAI's new frontend guide: strong constraints, moderate reasoning, ship. developers.openai.com/blog/designi...developers.openai.comDesigning delightful frontends with GPT-5.4 | OpenAI DevelopersPractical techniques for steering GPT-5.4 toward polished, production-ready frontend designs. 000
Olivier Balais @overnetcity.bsky.social · 28/03/2026OpenAI's Codex team starts meetings with unanswered questions. They fire off Codex threads in the background. 20 minutes later, answers are ready. Five or six questions per meeting, all handled by "little consultants working in the background." www.youtube.com/watch?v=Bo6G...youtube.comOpenAI: How AI is reshaping the craft of building software - The Pragmatic SummitTibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:… 000
Olivier Balais @overnetcity.bsky.social · 27/03/2026New practice at OpenAI: instead of debating trade-offs in a design doc, they spin up multiple implementations in parallel and pick the one that works best. When prototyping costs near-zero, "let's just try all three" beats "let's discuss which one." www.youtube.com/watch?v=Bo6G...youtube.comOpenAI: How AI is reshaping the craft of building software - The Pragmatic SummitTibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:… 000
Olivier Balais @overnetcity.bsky.social · 26/03/2026OpenAI's designers now ship more production code than engineers did 6 months ago. The models got good enough that designer-written code is mergeable as-is. Role boundaries aren't blurring. They're dissolving. www.youtube.com/watch?v=Bo6G...youtube.comOpenAI: How AI is reshaping the craft of building software - The Pragmatic SummitTibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:… 000
Olivier Balais @overnetcity.bsky.social · 25/03/2026More Magic Math from OpenAI? om.co/2026/03/23/m...om.coMore Magic Math from OpenAI?When it comes to OpenAI, smart money is starting to do the math out loud. And something doesn’t add up. On surface, today’s news that OpenAI is offering 17.5% guaranteed returns to priv… 000
Olivier Balais @overnetcity.bsky.social · 25/03/2026One PM runs the entire OpenAI Codex team. During a bug bash, he sent Codex to collect feedback, generate a Notion doc, file tickets in Linear, assign them, and follow up with everyone. One person doing the coordination work of five. AI doesn't just scale engineering. www.youtube.com/watch?v=Bo6G...youtube.comOpenAI: How AI is reshaping the craft of building software - The Pragmatic SummitTibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:… 010
Olivier Balais @overnetcity.bsky.social · 24/03/202630 engineers. 450M users. No code reviews. No Scrum. No Agile. No TDD. WhatsApp's secret? Brian Acton reviewed your first PR in extreme detail. After that, you were trusted. Meanwhile, Skype had 1,000 engineers and lost. www.youtube.com/watch?v=5Kn3...youtube.comBuilding WhatsApp with Jean LeeHow did a tiny team of 30 engineers build the world-famous messaging app more than a decade ago, and what can dev teams learn from that feat today? Jean Lee was engineer #19 at WhatsApp, joining when… 110
Olivier Balais @overnetcity.bsky.social · 23/03/2026Stripe built devboxes that spin up in 10s, 3M tests, sub-5s linting... all for human engineers. Turns out AI agents love the exact same things. Their "Minions" now ship 1,300 PRs/week. Best AI investment? Great developer experience. blog.bytebytego.com/p/how-stripe...blog.bytebytego.comHow Stripe’s Minions Ship 1,300 PRs a WeekEvery week, Stripe merges over 1,300 pull requests that contain zero human-written code. Not a single line. These PRs are produced by “Minions,” Stripe’s internal coding agents, which work completely… 110
Olivier Balais @overnetcity.bsky.social · 23/03/2026What does Staff Engineer look like in 2027? When agents write most of the code, expertise shifts. Less code craftsmanship. More architecture, orchestration, and judgment. The title stays. The job is being rewritten in real time. newsletter.pragmaticengineer.com/p/the-pulse-...newsletter.pragmaticengineer.comThe Pulse: What will the Staff Engineer role look like in 2027 and beyond?Also: new trend of token costs becoming a worry for CTOs, 10% cuts at Atlassian, and more. 000
Olivier Balais @overnetcity.bsky.social · 20/03/2026Claude Code now accounts for 4% of all public GitHub commits. DAUs doubled last month. This isn't an experiment. It's infrastructure. And it's 100% self-written. The tool that writes code is written by the code it writes. We're in a new era. 🔥 newsletter.pragmaticengineer.com/p/building-c...newsletter.pragmaticengineer.comBuilding Claude Code with Boris ChernyClaude Code creator Boris Cherny on building AI-powered coding tools, parallel agents, and how the engineer's role is evolving in an AI-first world. 000
Olivier Balais @overnetcity.bsky.social · 19/03/2026"Claude Code is now 100% written by Claude Code." - Boris Cherny, March 2026. → May 2025: 80% AI-generated → Dec 2025: 259 PRs in a month, zero IDE opened → Mar 2026: fully self-written The AI coding tool that improves itself. Let that sink in. 🔥officechai.comhttps://officechai.com/ai/claude-code-is-now-100-written-by-claude-code-creator-boris-cherny/ 010
Olivier Balais @overnetcity.bsky.social · 18/03/2026OpenAI just dropped GPT-5.4 mini and nano. The numbers: 400k context, 128k output, mini at $0.75/$4.50 per 1M tokens, nano at $0.20/$1.25. Nano edges past GPT-5 mini on SWE-Bench Pro. The small model race keeps accelerating.testingcatalog.comhttps://www.testingcatalog.com/openai-launches-gpt-5-4-mini-and-gpt-5-4-nano-on-apis/ 010
Olivier Balais @overnetcity.bsky.social · 18/03/2026Counter-intuitive: directors and senior leaders use Claude Code 2x more than junior devs. The people with the most context and judgment are going hardest on AI. Makes sense. AI amplifies expertise, it doesn't replace it.newsletter.pragmaticengineer.comhttps://newsletter.pragmaticengineer.com/p/ai-tooling-2026 020